Merge pull request #4 from anandhu-eng/cm_readme_inference_update

Updations for DLRM-v2
anandhu-eng · Aug 12, 2024 · 898ac2a · 898ac2a
2 parents 0bb503f + 5b0df15
commit 898ac2a
Show file tree

Hide file tree

Showing 3 changed files with 19 additions and 13 deletions.
diff --git a/docs/benchmarks/language/llama2-70b.md b/docs/benchmarks/language/llama2-70b.md
@@ -28,7 +28,7 @@ hide:
     ## Neural Magic MLPerf Implementation
 
     LLAMA2-70b-99
-{{ mlperf_inference_implementation_readme (4, "llama2-70b-99", "NeuralMagic") }}
+{{ mlperf_inference_implementation_readme (4, "llama2-70b-99", "neuralmagic") }}
 
     LLAMA2-70b-99.9
-{{ mlperf_inference_implementation_readme (4, "llama2-70b-99.9", "NeuralMagic") }}
+{{ mlperf_inference_implementation_readme (4, "llama2-70b-99.9", "neuralmagic") }}
diff --git a/docs/benchmarks/recommendation/dlrm-v2.md b/docs/benchmarks/recommendation/dlrm-v2.md
@@ -11,25 +11,25 @@ hide:
     ## MLPerf Reference Implementation in Python
 
     DLRM-v2-99
-{{ mlperf_inference_implementation_readme (4, "dlrm_v2-99", "reference") }}
+{{ mlperf_inference_implementation_readme (4, "dlrm-v2-99", "reference") }}
 
     DLRM-v2-99.9
-{{ mlperf_inference_implementation_readme (4, "dlrm_v2-99.9", "reference") }}
+{{ mlperf_inference_implementation_readme (4, "dlrm-v2-99.9", "reference") }}
 
 === "Nvidia"
     ## Nvidia MLPerf Implementation
 
     DLRM-v2-99
-{{ mlperf_inference_implementation_readme (4, "dlrm_v2-99", "nvidia") }}
+{{ mlperf_inference_implementation_readme (4, "dlrm-v2-99", "nvidia") }}
 
     DLRM-v2-99.9
-{{ mlperf_inference_implementation_readme (4, "dlrm_v2-99.9", "nvidia") }}
+{{ mlperf_inference_implementation_readme (4, "dlrm-v2-99.9", "nvidia") }}
 
 === "Intel"
     ## Intel MLPerf Implementation
 
     DLRM-v2-99
-{{ mlperf_inference_implementation_readme (4, "dlrm_v2-99", "intel") }}
+{{ mlperf_inference_implementation_readme (4, "dlrm-v2-99", "intel") }}
 
     DLRM-v2-99.9
-{{ mlperf_inference_implementation_readme (4, "dlrm_v2-99.9", "intel") }}
+{{ mlperf_inference_implementation_readme (4, "dlrm-v2-99.9", "intel") }}
diff --git a/main.py b/main.py
@@ -34,12 +34,12 @@ def mlperf_inference_implementation_readme(spaces, model, implementation):
             devices = [ "CUDA" ]
             frameworks = [ "TensorRT" ]
 
-        elif implementation == "NeuralMagic":
+        elif implementation == "neuralmagic":
             devices = [ "CUDA" ]
-            frameworks = [ "vLLM" ]
+            frameworks = [ "pytorch" ]
 
         elif implementation == "intel":
-            if model not in [ "bert-99", "bert-99.9", "gptj-99", "gptj-99.9", "resnet50", "retinanet", "3d-unet-99", "3d-unet-99.9", "dlrm_v2-99", "dlrm_v2-99.9" ]:
+            if model not in [ "bert-99", "bert-99.9", "gptj-99", "gptj-99.9", "resnet50", "retinanet", "3d-unet-99", "3d-unet-99.9", "dlrm-v2-99", "dlrm-v2-99.9" ]:
                  return pre_space+"    WIP"
             if model in [ "bert-99", "bert-99.9", "retinanet", "3d-unet-99", "3d-unet-99.9" ]:
                  code_version="r4.0"
@@ -269,11 +269,14 @@ def mlperf_inference_run_command(spaces, model, implementation, framework, categ
             docker_cmd_suffix += f" \\\n{pre_space} --test_query_count={test_query_count}"
 
             if "llama2-70b" in model:
-                if implementation != "NeuralMagic":
+                if implementation != "neuralmagic":
                     docker_cmd_suffix += f" \\\n{pre_space} --tp_size=<TP_SIZE>"
                     docker_cmd_suffix += f" \\\n{pre_space} --nvidia_llama2_dataset_file_path=<PATH_TO_PICKE_FILE>"
                 else:
                     docker_cmd_suffix += f" \\\n{pre_space} --api_server=<API_SERVER_URL>"
+
+            if "dlrm-v2" in model and implementation == "nvidia":
+                docker_cmd_suffix += f" \\\n{pre_space} --criteo_day23_raw_data_path=<PATH_TO_CRITEO_DAY23_RAW_DATA>"
 
             docker_setup_cmd = f"""\n
 {f_pre_space}```bash
@@ -295,11 +298,14 @@ def mlperf_inference_run_command(spaces, model, implementation, framework, categ
                 cmd_suffix += f" \\\n {pre_space} --test_query_count={test_query_count}"
 
             if "llama2-70b" in model:
-                if implementation != "NeuralMagic":
+                if implementation != "neuralmagic":
                     cmd_suffix += f" \\\n{pre_space} --tp_size=<TP_SIZE>"
                     cmd_suffix += f" \\\n{pre_space} --nvidia_llama2_dataset_file_path=<PATH_TO_PICKE_FILE>"
                 else:
                     cmd_suffix += f" \\\n{pre_space} --api_server=<API_SERVER_URL>"
+
+            if "dlrm-v2" in model and implementation == "nvidia":
+                cmd_suffix += f" \\\n{pre_space} --criteo_day23_raw_data_path=<PATH_TO_CRITEO_DAY23_RAW_DATA>"
 
             run_cmd = f"""\n
 {f_pre_space}```bash